Developer Tools

looprepo.dev

Manages and evaluates agent-loop prompts for AI coding assistants.

1 endpoint22 known toolsFirst detected July 24, 2026Last detected September 4, 2026

ENDPOINT 1

https://mcp.looprepo.dev/mcp

No auth detected

MCP server metadata

Name: looprepo
Version: 1.1.0

Capabilities

tools

Server instructions

Search 143 vetted agent loops for Claude Code/Codex across 22 tools: discovery (search, trending, similar, for-your-stack, compare), deterministic A–F safety grading (loops_grade, loops_harden, harness_validate), Claude-use intake → loop recommendations (loops_intake_recommend), plain-language loop crafting (loops_craft), guides (articles_search), review-gated community submissions (loops_submit), and complete safe-loop harness bundles (loops_generate_harness). Start with loops_categories, loops_search, or loops_intake_recommend.

Known tools 22

loops_search

Search the looprepo directory of agent loops (/loop, /goal, /schedule, Ralph-style) for Claude Code and Codex.

Inferred read-only

loops_grade

Grade any agent-loop prompt A–F with the same deterministic, default-fail Safety Score that gates the looprepo directory.

Inferred read-only

loops_get

Get one loop by slug: full prompt, usage notes (when to use / how it works / safety), attribution, and stats.

Inferred read-only

loops_categories

List all categories and loop types with published-loop counts.

Inferred read-only

loops_intake_recommend

Given a read-only intake report pasted from Claude, Claude Code, Cowork, Codex, or another agent, infer the goal/workflows and return ranked real looprepo loops plus a harness-ready builder prefill.

Inferred read-only

loops_generate_harness

Generate a complete safe-loop harness bundle.

Inferred read-only

loops_trending

Top loops by upvotes + copies over a recent window.

Inferred read-only

loops_similar

Loops related to a given slug — same category, matching intent, and text similarity.

Inferred read-only

loops_for_stack

Describe your tools/stack (e.g.

Inferred read-only

loops_compare

Compare 2–3 loops side by side: safety grade/score, type, risk, and boundedness signals.

Inferred read-only

loops_stats

Directory-wide stats: totals, category/type breakdown, safety-grade distribution, newest loops.

Inferred read-only

loops_of_the_week

The top loop of the trailing 7 days plus recent A/B-grade picks.

Inferred read-only

articles_search

Search looprepo's published guides/articles on loop engineering.

Inferred read-only

articles_get

Fetch one published guide: full markdown body plus metadata.

Inferred read-only

loops_submit

Submit a community loop to the review queue.

Inferred read-only

intake_prompt_get

Returns the read-only Claude-use intake prompt.

Inferred read-only

harness_validate

Deterministically validates the persistent harness separately from the loop running inside it, then diagnoses likely failure modes.

Inferred read-only

loops_harden

Deterministic grade plus the exact edits to reach the next grade (exit condition, turn cap, verification, scope).

Inferred read-only

loops_grade_explain

Deterministic A–F grade plus an AI-written explanation and top-3 edits.

Inferred read-only

loops_craft

Describe a workflow in plain language and get one safe, copy-paste loop prompt with verification, stop conditions, and approval gates.

Inferred read-only

cme_tier_status

Your current tier (anonymous or CME Pro/Power), daily limits, and today's usage of crafted loops and harness builds.

Inferred read-only

beacon_run_report

Recent loop runs for your Mission Control beacon token: status, exit reason, turns, cost.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.looprepo]
url = "https://mcp.looprepo.dev/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "looprepo": {
      "type": "http",
      "url": "https://mcp.looprepo.dev/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: looprepo
Remote MCP URL: https://mcp.looprepo.dev/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "looprepo": {
      "url": "https://mcp.looprepo.dev/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "looprepo": {
      "type": "http",
      "url": "https://mcp.looprepo.dev/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "looprepo",
  "transport": "streamable-http",
  "url": "https://mcp.looprepo.dev/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for looprepo.dev was fetched 2026-08-29T02:24:47.618Z.

Trust status Neutral

looprepo.dev is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.